Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2559 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.6563. Min Act: -0.1700

Data Index: 3870257 (Open Web Text)

Max Activating Token Index: 529

Text #1

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.6508. Min Act: -0.1699

Data Index: 2793677 (Open Web Text)

Max Activating Token Index: 689

Text #2

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.6363. Min Act: -0.1700

Data Index: 1539675 (Open Web Text)

Max Activating Token Index: 627

Text #3

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.5989. Min Act: -0.1699

Data Index: 5210328 (Open Web Text)

Max Activating Token Index: 572

Text #4

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.6055. Min Act: -0.1700

Data Index: 3888270 (Open Web Text)

Max Activating Token Index: 874

Text #5

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.6193. Min Act: -0.1700

Data Index: 2440294 (Open Web Text)

Max Activating Token Index: 560

Text #6

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.6048. Min Act: -0.1700

Data Index: 6719706 (Open Web Text)

Max Activating Token Index: 989

Text #7

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.5977. Min Act: -0.1700

Data Index: 2449283 (Open Web Text)

Max Activating Token Index: 594

Text #8

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.5801. Min Act: -0.1700

Data Index: 341463 (Open Web Text)

Max Activating Token Index: 314

Text #9

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.5978. Min Act: -0.1700

Data Index: 1982520 (Open Web Text)

Max Activating Token Index: 656

Text #10

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.5792. Min Act: -0.1700

Data Index: 566967 (Open Web Text)

Max Activating Token Index: 782

Text #11

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.5791. Min Act: -0.1700

Data Index: 5117302 (Open Web Text)

Max Activating Token Index: 24

Text #12

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.5866. Min Act: -0.1699

Data Index: 3475093 (Open Web Text)

Max Activating Token Index: 149

Text #13

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.5924. Min Act: -0.1700

Data Index: 3432958 (Open Web Text)

Max Activating Token Index: 543

Text #14

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.5860. Min Act: -0.1700

Data Index: 8750857 (Open Web Text)

Max Activating Token Index: 199

Text #15

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.5729. Min Act: -0.1700

Data Index: 6410644 (Open Web Text)

Max Activating Token Index: 479

Text #16

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.5658. Min Act: -0.1664

Data Index: 8210977 (Open Web Text)

Max Activating Token Index: 660

Text #17

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.5807. Min Act: -0.1700

Data Index: 1828695 (Open Web Text)

Max Activating Token Index: 993

Text #18

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.5854. Min Act: -0.1700

Data Index: 5289942 (Open Web Text)

Max Activating Token Index: 577

Text #19

Max Range: 1.6563. Min Range: -1.6563

Max Act: 1.5656. Min Act: -0.1699

Data Index: 6094115 (Open Web Text)

Max Activating Token Index: 941